437 reputation
29
bio website
location Utah
age
visits member for 1 year, 1 month
seen 6 hours ago
stats profile views 22

7h
comment multiple regression analysis
This question has been answered before. Look under the Related Header to the right.
May
8
comment Variance of a time series fitted to an ARIMA model
I think the variance of the fitted values is is: var(demandts.train.arima.fit) which is also different
May
8
comment Variance of a time series fitted to an ARIMA model
So as you see the sigma2 is different from the variance of your x variable, also it is different from the variance of the residuals: var(residuals(demandts.train.arima)).
May
7
answered Variance of a time series fitted to an ARIMA model
Apr
25
comment How to draw the regression line and the scatterplot between observed and predicted in R
If the observed and the predicted were very close to each other they would be on a diagonal line on your plot. So you may just want to add abline(0,1) after your plot above?
Apr
15
awarded  Yearling
Feb
23
revised Type of Distribution
deleted 4 characters in body
Feb
21
answered Type of Distribution
Nov
12
comment Independence test for values between 0 and 1
Do your observations represent the number of events over the same number of trials?
Aug
9
comment Does anyone know how this visualization was made?
the language "processing" can do interactive graphics and 3d. There are examples at both processing.org and openprocessing.org.
Aug
8
revised How to generate nice summary table?
added 33 characters in body
Aug
7
revised How to generate nice summary table?
added 66 characters in body
Aug
7
answered How to generate nice summary table?
Aug
1
comment R/Bayes: Why is a wildly different prior not affecting the posterior in bayesglm{arm}?
Your data has 2000 points. If the data has high precision and large N this is what I would expect. If you sample the data down to just 50 observations, the estimates change more with different priors.
Jul
31
awarded  Citizen Patrol
Jul
26
comment What's the distribution of these data?
+1 Mixture models are useful. Especially if you have data that is generated under two or more different circumstances.
Jul
26
comment What's the distribution of these data?
@Macro Many 'off the shelf' distributions can handle both skewed and heavy tailed situations. F and Gamma come to mind, along with nearly all 3 and 4 parameter distributions. I just added an answer so the original poster would have an idea about how to quantify the 'goodness of fit', and make numerical comparisons.
Jul
26
answered What's the distribution of these data?
Jul
5
revised How to test the statistical significance for categorical variable in linear regression?
fixing the code listing
Jul
5
suggested suggested edit on How to test the statistical significance for categorical variable in linear regression?